Commit
•
70b8ccf
1
Parent(s):
c2f6196
Training in progress, epoch 1
Browse files- config.json +1 -1
- last-checkpoint/config.json +1 -1
- last-checkpoint/optimizer.pt +2 -2
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +20 -99
- last-checkpoint/training_args.bin +1 -1
- pytorch_model.bin +1 -1
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base",
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
last-checkpoint/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "facebook/wav2vec2-base",
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e6a9f09e6fb63ad751dc4611e137ce1869f410c418fa9bfaad1418641415acc
|
3 |
+
size 721661957
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377646433
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:280f8c091473f4d05ea40cb0c88ed010f67a742293a0a7a41cd0ee9528191e96
|
3 |
size 377646433
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5826ea72677989986439d9f551db7e4c81ec8600b7258910ddfb9d4f9272c47
|
3 |
size 14575
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 557
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe7c767111accfefd8c962f6b3f65e0837fac0d4f2fb9b95baf14515e7dae4e1
|
3 |
size 557
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69329aa5f5ce6722e627e837927ad2e18f7a9b9c2acd8a4165059b6ad1f66c71
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,112 +1,33 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
-
"epoch":
|
12 |
-
"learning_rate": 9.
|
13 |
-
"loss":
|
14 |
-
"step":
|
15 |
-
},
|
16 |
-
{
|
17 |
-
"epoch":
|
18 |
-
"eval_cer": 0.
|
19 |
-
"eval_loss":
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
|
26 |
-
{
|
27 |
-
"epoch": 20.0,
|
28 |
-
"learning_rate": 8.421915444348577e-05,
|
29 |
-
"loss": 0.198,
|
30 |
-
"step": 85400
|
31 |
-
},
|
32 |
-
{
|
33 |
-
"epoch": 20.0,
|
34 |
-
"eval_cer": 0.1038961038961039,
|
35 |
-
"eval_loss": 1.091776728630066,
|
36 |
-
"eval_runtime": 7.7941,
|
37 |
-
"eval_samples_per_second": 26.943,
|
38 |
-
"eval_steps_per_second": 3.464,
|
39 |
-
"eval_wer": 0.19523809523809524,
|
40 |
-
"step": 85400
|
41 |
-
},
|
42 |
-
{
|
43 |
-
"epoch": 21.0,
|
44 |
-
"learning_rate": 3.1609351246969886e-05,
|
45 |
-
"loss": 0.0837,
|
46 |
-
"step": 89670
|
47 |
-
},
|
48 |
-
{
|
49 |
-
"epoch": 21.0,
|
50 |
-
"eval_cer": 0.11082251082251082,
|
51 |
-
"eval_loss": 1.0681313276290894,
|
52 |
-
"eval_runtime": 7.6465,
|
53 |
-
"eval_samples_per_second": 27.464,
|
54 |
-
"eval_steps_per_second": 3.531,
|
55 |
-
"eval_wer": 0.1761904761904762,
|
56 |
-
"step": 89670
|
57 |
-
},
|
58 |
-
{
|
59 |
-
"epoch": 24.0,
|
60 |
-
"learning_rate": 2.1086322363285264e-05,
|
61 |
-
"loss": 0.061,
|
62 |
-
"step": 102480
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"epoch": 24.0,
|
66 |
-
"eval_cer": 0.16363636363636364,
|
67 |
-
"eval_loss": 1.676707148551941,
|
68 |
-
"eval_runtime": 7.6904,
|
69 |
-
"eval_samples_per_second": 27.307,
|
70 |
-
"eval_steps_per_second": 3.511,
|
71 |
-
"eval_wer": 0.24285714285714285,
|
72 |
-
"step": 102480
|
73 |
-
},
|
74 |
-
{
|
75 |
-
"epoch": 27.0,
|
76 |
-
"learning_rate": 1.0564115206047907e-05,
|
77 |
-
"loss": 0.0445,
|
78 |
-
"step": 115290
|
79 |
-
},
|
80 |
-
{
|
81 |
-
"epoch": 27.0,
|
82 |
-
"eval_cer": 0.10562770562770563,
|
83 |
-
"eval_loss": 1.3365751504898071,
|
84 |
-
"eval_runtime": 7.6936,
|
85 |
-
"eval_samples_per_second": 27.295,
|
86 |
-
"eval_steps_per_second": 3.509,
|
87 |
-
"eval_wer": 0.14285714285714285,
|
88 |
-
"step": 115290
|
89 |
-
},
|
90 |
-
{
|
91 |
-
"epoch": 30.0,
|
92 |
-
"learning_rate": 4.190804881055097e-08,
|
93 |
-
"loss": 0.0337,
|
94 |
-
"step": 128100
|
95 |
-
},
|
96 |
-
{
|
97 |
-
"epoch": 30.0,
|
98 |
-
"eval_cer": 0.10043290043290043,
|
99 |
-
"eval_loss": 1.295832633972168,
|
100 |
-
"eval_runtime": 7.6185,
|
101 |
-
"eval_samples_per_second": 27.564,
|
102 |
-
"eval_steps_per_second": 3.544,
|
103 |
-
"eval_wer": 0.14285714285714285,
|
104 |
-
"step": 128100
|
105 |
}
|
106 |
],
|
107 |
-
"max_steps":
|
108 |
-
"num_train_epochs":
|
109 |
-
"total_flos":
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|
112 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 4270,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"learning_rate": 9.825795424664739e-05,
|
13 |
+
"loss": 7.2959,
|
14 |
+
"step": 4270
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_cer": 0.5922077922077922,
|
19 |
+
"eval_loss": 1.3762445449829102,
|
20 |
+
"eval_new_wer": 0.3952380952380952,
|
21 |
+
"eval_old_wer": 1.0,
|
22 |
+
"eval_runtime": 7.8519,
|
23 |
+
"eval_samples_per_second": 26.745,
|
24 |
+
"eval_steps_per_second": 3.439,
|
25 |
+
"step": 4270
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
}
|
27 |
],
|
28 |
+
"max_steps": 64050,
|
29 |
+
"num_train_epochs": 15,
|
30 |
+
"total_flos": 3.3863997052324454e+18,
|
31 |
"trial_name": null,
|
32 |
"trial_params": null
|
33 |
}
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3451
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40b73e2d38557903613d82a7f7939cc536f83ca7910211be0f74d26aab9d8c03
|
3 |
size 3451
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 377646433
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:280f8c091473f4d05ea40cb0c88ed010f67a742293a0a7a41cd0ee9528191e96
|
3 |
size 377646433
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3451
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40b73e2d38557903613d82a7f7939cc536f83ca7910211be0f74d26aab9d8c03
|
3 |
size 3451
|